OpenClaw AI 技能

创建 AI images with GPT Image, Gemini Nano Banana, FLUX, Imagen, and top 提供者s using prompt engineering, style control, and smart editing.

Edit images with AI inpAInting, outpAInting, background removal, upscaling, and restoration 工具s.

Analyze and interpret images by describing content, 提取ing text, answering questions, comparing visuals, and 提取ing structured data from JPG, PNG, GI...

Still-to-video conversion 图形界面de: 模型 selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, 种子ance, Fabric, Grok Video with when to use

AI image prompt 优化器. 生成 and enhance prompts for Midjourney, DALL-E, and Stable Diffusion. Includes prompt enhancement.

提取 text from images using OCR with support for Chinese and English in common 格式化s like jpg, png, and jpeg.

Up扩展 and enhance images with Real-ESRGAN, Thera, Topaz, FLUX Up扩展r via inference.sh 命令行工具. 模型s: Real-ESRGAN, Thera (any size), FLUX Dev Up扩展r, Topa...

智谱 GLM-4.6V 多模态视觉模型集成插件。支持 128K 长上下文、文档解析、视频理解与原生工具调用。具备工业级安全审计指引。

Image Generation via Coze | 基于 Coze 的图像生成技能 生成 images using Coze 工作流s. 使用 种子ream 4.5 模型. Handles parameter building and 结果 parsing. 负责参数构...

Turn a source image (or multi-color mask image) into a 3D-printable bas-relief STL by m应用ing colors (or gray扩展) to heights. Use when you have an image

Analyzes images to 检测 AI generation, 提取 metadata, identify artifacts, and perform content moderation using local and cloud-based 工具s.

Resize images using ImageMagick (命令行工具). Entrypoint is a Bash script.

Crop objects from images using bounding box annotations in COCO, YOLO, VOC, or LabelMe 格式化s with optional p添加ing and batch processing.

Visual image 搜索 using Google Lens via SerpAPI. Identify objects, landmarks, products, plants, animals, artwork, 记录os, or any visual entity from an ima

生成 professional AI image prompts for any 平台 and niche — Instagram, LinkedIn, b记录 headers, YouTube thumbnAIls, brand visuals, and ads. Works with...

图片识别 - 通用图片识别技能，支持 OCR 文字提取、物体识别、场景分析等。自动使用用户配置的视觉模型，适用于 Android/Termux 环境。

Image recognition and understanding 工具. Uses a multimodal 模型 (e.g. doubao-种子-2.0-pro, kimi-k2.5) to analyze image content and supports OCR text extrac

将图片（含文字、公式、标题）转换为指定代码格式。自动识别标题级别（title1/title2/title3），文字行转为 $word->body("正文=".$F);，公式转为 $word->formula("");，图片标记为 ![image]

When the user wants to 优化 images for 搜索 engines and performance. Also use when the user mentions "image SEO," "alt text," "image captions," "figcap...

Reference 工具 for dev工具s — covers intro, quick启动, patterns and more. Quick lookup for Image Labeler concepts, best practices, and implementation patter